Search

Background: Pancreatic cysts in autosomal dominant polycystic kidney disease (ADPKD) correlate with PKD2 mutations, which have a different phenotype than PKD1 mutations. However, pancreatic cysts are commonly overlooked by radiologists. Here, we automate the detection of pancreatic cysts on abdominal MRI in ADPKD. Methods: Eight nnU-Net-based segmentation models with 2D or 3D configuration and various loss functions were trained on positive-only or positive-and-negative datasets, comprising axial and coronal T2-weighted MR images from 254 scans on 146 ADPKD patients with pancreatic cysts labeled independently by two radiologists. Model performance was evaluated on test subjects unseen in training, comprising 40 internal, 40 external, and 23 test–retest reproducibility ADPKD patients. Results: Two radiologists agreed on 52% of cysts labeled on training data, and 33%/25% on internal/external test datasets. The 2D model with a loss of combined dice similarity coefficient and cross-entropy trained with the dataset with both positive and negative cases produced an optimal dice score of 0.7 ± 0.5/0.8 ± 0.4 at the voxel level on internal/external validation and was thus used as the best-performing model. In the test–retest, the optimal model showed superior reproducibility (83% agreement between scan A and B) in segmenting pancreatic cysts compared to six expert observers (77% agreement). In the internal/external validation, the optimal model showed high specificity of 94%/100% but limited sensitivity of 20%/24%. Conclusions: Labeling pancreatic cysts on T2 images of the abdomen in patients with ADPKD is challenging, deep learning can help the automated detection of pancreatic cysts, and further image quality improvement is warranted. [ABSTRACT FROM AUTHOR]

Abdominal imaging of autosomal dominant polycystic kidney disease (ADPKD) has historically focused on detecting complications such as cyst rupture, cyst infection, obstructing renal calculi, and pyelonephritis; discriminating complex cysts from renal cell carcinoma; and identifying sources of abdominal pain. Many imaging features of ADPKD are incompletely evaluated or not deemed to be clinically significant, and because of this, treatment options are limited. However, total kidney volume (TKV) measurement has become important for assessing the risk of disease progression (i.e., Mayo Imaging Classification) and predicting tolvaptan treatment's efficacy. Deep learning for segmenting the kidneys has improved these measurements' speed, accuracy, and reproducibility. Deep learning models can also segment other organs and tissues, extracting additional biomarkers to characterize the extent to which extrarenal manifestations complicate ADPKD. In this concept paper, we demonstrate how deep learning may be applied to measure the TKV and how it can be extended to measure additional features of this disease. [ABSTRACT FROM AUTHOR]

Total kidney volume measured on MRI is an important biomarker for assessing the progression of autosomal dominant polycystic kidney disease and response to treatment. However, we have noticed that there can be substantial differences in the kidney volume measurements obtained from the various pulse sequences commonly included in an MRI exam. Here we examine kidney volume measurement variability among five commonly acquired MRI pulse sequences in abdominal MRI exams in 105 patients with ADPKD. Right and left kidney volumes were independently measured by three expert observers using model-assisted segmentation for axial T2, coronal T2, axial single-shot fast spin echo (SSFP), coronal SSFP, and axial 3D T1 images obtained on a single MRI from ADPKD patients. Outlier measurements were analyzed for data acquisition errors. Most of the outlier values (88%) were due to breathing during scanning causing slice misregistration with gaps or duplication of imaging slices (n = 35), slice misregistration from using multiple breath holds during acquisition (n = 25), composing of two overlapping acquisitions (n = 17), or kidneys not entirely within the field of view (n = 4). After excluding outlier measurements, the coefficient of variation among the five measurements decreased from 4.6% pre to 3.2%. Compared to the average of all sequences without errors, TKV measured on axial and coronal T2 weighted imaging were 1.2% and 1.8% greater, axial SSFP was 0.4% greater, coronal SSFP was 1.7% lower and axial T1 was 1.5% lower than the mean, indicating intrinsic measurement biases related to the different MRI contrast mechanisms. In conclusion, MRI data acquisition errors are common but can be identified using outlier analysis and excluded to improve organ volume measurement consistency. Bias toward larger volume measurements on T2 sequences and smaller volumes on axial T1 sequences can also be mitigated by averaging data from all error-free sequences acquired. [ABSTRACT FROM AUTHOR]

Solid electrolyte interphase (SEI) formation and H2O activity reduction in Water‐in‐Salt electrolytes (WiSE) with an enlarged stability window of 3.0 V have provided the feasibility of the high‐energy‐density aqueous Li‐ion batteries. Here, we extend the cathodic potential of WiSE by rationally controlling intermolecular interaction and interphase chemistry with the introduction of trimethyl phosphate (TMP) into WiSE. The TMP not merely limits the H2O activity via the strong interaction between TMP and H2O but also contributes to the formation of reinforced SEI involving phosphate and LiF by manipulating the Li+ solvation structure. Thus, water‐tolerance LiMn2O4 (LMO)||Li4Ti5O12 (LTO) full cell with a P/N ratio of 1.14 can be assembled and achieve a long cycling life of 1000 times with high coulombic efficiency of >99.9 %. This work provides a promising insight into the cost‐effective practical manufacture of LMO||LTO cells without rigorous moisture‐free requirements. [ABSTRACT FROM AUTHOR]

To drive electrical vehicles for long‐range, the energy density of Li‐ion batteries must be further enhanced, which requires high‐energy cathode materials. Among them, Ni‐rich LiNixMnyCo1−x–yO2 (x > 0.5, NMC) is one of the most promising candidates. However, traditional poly‐crystal (PC) NMC materials, whose particles are secondary clusters consisting of many primary crystalline particles, are susceptible to pulverization along the inter grain/particle boundaries, resulting in poor cycle stability. Recently, single crystal (SC)‐NMC cathodes are proposed as they are believed to have several merits such as high structural integrity, lower interface with electrolyte, and potentially better energy storage performance. Nevertheless, several queries, such as the merits of SC structure and the mechanism for their structure degradation, are still controversial and required to be addressed. Herein, the synthesis parameters, properties, energy storage as well as safety of SC‐ and PC‐NMC cathodes with various Ni contents are critically reviewed, for clarifying the merits and drawbacks of SC. Furthermore, the study focuses on the recent advances of insight mechanisms and strategies for stabilizing the structure/interface by doping, morphology engineering, surface coating, and composition tailoring. The remaining challenges, safety concerns, and perspectives to enhance the electrochemical performance of SC‐NMC cathodes for electric vehicle application are followed. [ABSTRACT FROM AUTHOR]

An increased interest in longitudinal neurodevelopment during the first few years after birth has emerged in recent years. Noninvasive magnetic resonance imaging (MRI) can provide crucial information about the development of brain structures in the early months of life. Despite the success of MRI collections and analysis for adults, it remains a challenge for researchers to collect high-quality multimodal MRIs from developing infant brains because of their irregular sleep pattern, limited attention, inability to follow instructions to stay still during scanning. In addition, there are limited analytic approaches available. These challenges often lead to a significant reduction of usable MRI scans and pose a problem for modeling neurodevelopmental trajectories. Researchers have explored solving this problem by synthesizing realistic MRIs to replace corrupted ones. Among synthesis methods, the convolutional neural network-based (CNN-based) generative adversarial networks (GANs) have demonstrated promising performance. In this study, we introduced a novel 3D MRI synthesis framework– pyramid transformer network (PTNet3D)– which relies on attention mechanisms through transformer and performer layers. We conducted extensive experiments on high-resolution Developing Human Connectome Project (dHCP) and longitudinal Baby Connectome Project (BCP) datasets. Compared with CNN-based GANs, PTNet3D consistently shows superior synthesis accuracy and superior generalization on two independent, large-scale infant brain MRI datasets. Notably, we demonstrate that PTNet3D synthesized more realistic scans than CNN-based models when the input is from multi-age subjects. Potential applications of PTNet3D include synthesizing corrupted or missing images. By replacing corrupted scans with synthesized ones, we observed significant improvement in infant whole brain segmentation. [ABSTRACT FROM AUTHOR]

LiNixCoyMnzO2 (x+y+z=1)||graphite lithium‐ion battery (LIB) chemistry promises practical applications. However, its low‐temperature (≤ −20 °C) performance is poor because the increased resistance encountered by Li+ transport in and across the bulk electrolytes and the electrolyte/electrode interphases induces capacity loss and battery failures. Though tremendous efforts have been made, there is still no effective way to reduce the charge transfer resistance (Rct) which dominates low‐temperature LIBs performance. Herein, we propose a strategy of using low‐polarity‐solvent electrolytes which have weak interactions between the solvents and the Li+ to reduce Rct, achieving facile Li+ transport at sub‐zero temperatures. The exemplary electrolyte enables LiNi0.8Mn0.1Co0.1O2||graphite cells to deliver a capacity of ≈113 mAh g−1 (98 % full‐cell capacity) at 25 °C and to remain 82 % of their room‐temperature capacity at −20 °C without lithium plating at 1/3C. They also retain 84 % of their capacity at −30 °C and 78 % of their capacity at −40 °C and show stable cycling at 50 °C. [ABSTRACT FROM AUTHOR]

The capacity of transition metal oxide cathode for Li‐ion batteries can be further enhanced by increasing the charging potential. However, these high voltage cathodes suffer from fast capacity decay because the large volume change of cathode breaks the active materials and cathode‐electrolyte interphase (CEI), resulting in electrolyte penetration into broken active materials and continuous side reactions between cathode and electrolytes. Herein, a robust LiF‐rich CEI was formed by potentiostatic reduction of fluorinated electrolyte at a low potential of 1.7 V. By taking LiCoO2 as a model cathode, we demonstrate that the LiF‐rich CEI maintains the structural integrity and suppresses electrolyte penetration at a high cut‐off potential of 4.6 V. The LiCoO2 with LiF‐rich CEI exhibited a capacity of 198 mAh g−1 at 0.5C and an enhanced capacity retention of 63.5 % over 400 cycles as compared to the LiF‐free LiCoO2 with only 17.4 % of capacity retention. [ABSTRACT FROM AUTHOR]

The instability of sulfide solid electrolytes to Li anode and high‐voltage LiNi0.8Mn0.1Co0.1O2 (NMC811) cathodes limits the cyclic performance of all‐solid‐state lithium battery (ASSLB). Herein, the stability of Li6PS5Cl against Li anode is enhanced by mixing a small amount (0.32 wt%) of CuF2‐LiNO3 (CL) into Li6PS5Cl electrolyte layer to in‐situ form a mixed‐conductive‐lithiophobic and self‐healing LiF‐Li3N‐Cu solid electrolyte interphase (SEI) at Li6PS5Cl‐CL/Li interface. The critical current density (CCD) of Li6PS5Cl‐CuF2‐LiNO3 increases to 1.4 mA cm–2/1.4 mAh cm–2 at room temperature, which is much higher than that of pristine Li6PS5Cl (0.4 mA cm–2/0.4 mAh cm–2) even though mixing 0.32 wt% CL into Li6PS5Cl slightly reduces the ionic conductivity from 2.9 × 10–3 to 1.5 × 10–3 S cm–1. The compatibility of Li6PS5Cl‐CL electrolyte to single‐crystalline NMC811 (S‐NMC811) is further enhanced by adding a small amount (0.02 wt%) of AlF3 into Li6PS5Cl‐CL forming Li6PS5Cl‐CuF2‐LiNO3‐AlF3 (Li6PS5Cl‐CLA) as a cathode electrolyte and by doing Cl– on S‐NMC811 (Cl@S‐NMC811) surface. The Cl@S‐NMC811‐Li6PS5Cl‐CLA|Li6PS5Cl‐CL|Li cells with areal capacity of 2.55 mAh cm‐2 achieve a capacity retention of 69.4% after 100 cycles at 1C (1C = 200 mAh g‐1). Adding a small amount of SEI and cathode/electrolyte interphase (CEI) former into the sulfide electrolytes with minimal reduction (48.3%) of ionic conductivity is an effective method to enhance the performance of ASSLB. [ABSTRACT FROM AUTHOR]

Automatic delineation of skin lesion contours from dermoscopy images is a basic step in the process of diagnosis and treatment of skin lesions. However, it is a challenging task due to the high variation of appearances and sizes of skin lesions. In order to deal with such challenges, we propose a new dense deconvolutional network (DDN) for skin lesion segmentation based on residual learning. Specifically, the proposed network consists of dense deconvolutional layers (DDLs), chained residual pooling (CRP), and hierarchical supervision (HS). First, unlike traditional deconvolutional layers, DDLs are adopted to maintain the dimensions of the input and output images unchanged. The DDNs are trained in an end-to-end manner without the need of prior knowledge or complicated postprocessing procedures. Second, the CRP aims to capture rich contextual background information and to fuse multilevel features. By combining the local and global contextual information via multilevel feature fusion, the high-resolution prediction output is obtained. Third, HS is added to serve as an auxiliary loss and to refine the prediction mask. Extensive experiments based on the public ISBI 2016 and 2017 skin lesion challenge datasets demonstrate the superior segmentation results of our proposed method over the state-of-the-art methods. [ABSTRACT FROM AUTHOR]

Abstract: Organic electrode materials are promising for green and sustainable lithium‐ion batteries. However, the high solubility of organic materials in the liquid electrolyte results in the shuttle reaction and fast capacity decay. Herein, azo compounds are firstly applied in all‐solid‐state lithium batteries (ASSLB) to suppress the dissolution challenge. Due to the high compatibility of azobenzene (AB) based compounds to Li3PS4 (LPS) solid electrolyte, the LPS solid electrolyte is used to prevent the dissolution and shuttle reaction of AB. To maintain the low interface resistance during the large volume change upon cycling, a carboxylate group is added into AB to provide 4‐(phenylazo) benzoic acid lithium salt (PBALS), which could bond with LPS solid electrolyte via the ionic bonding between oxygen in PBALS and lithium ion in LPS. The ionic bonding between the active material and solid electrolyte stabilizes the contact interface and enables the stable cycle life of PBALS in ASSLB. [ABSTRACT FROM AUTHOR]

Background: Dermoscopy imaging has been a routine examination approach for skin lesion diagnosis. Accurate segmentation is the first step for automatic dermoscopy image assessment.Objective: The main challenges for skin lesion segmentation are numerous variations in viewpoint and scale of skin lesion region.Methods: To handle these challenges, we propose a novel skin lesion segmentation network via a very deep dense deconvolution network based on dermoscopic images. Specifically, the deep dense layer and generic multi-path Deep RefineNet are combined to improve the segmentation performance. The deep representation of all available layers is aggregated to form the global feature maps using skip connection. Also, the dense deconvolution layer is leveraged to capture diverse appearance features via the contextual information. Finally, we apply the dense deconvolution layer to smooth segmentation maps and obtain final high-resolution output.Results: Our proposed method shows the superiority over the state-of-the-art approaches based on the public available 2016 and 2017 skin lesion challenge dataset and achieves the accuracy of 96.0% and 93.9%, which obtained a 6.0% and 1.2% increase over the traditional method, respectively.Conclusions: By utilizing Dense Deconvolution Net, the average time for processing one testing images with our proposed framework was 0.253 s. [ABSTRACT FROM AUTHOR]

• We propose an FTN which is fully relied on Transformer. • We leverage sliding window tokenization to construct hierarchical features. • Spatial Pyramid Transformer to increase efficiency. • Transformer Decoder is proposed to aggregate hierarchical features. Automatic skin lesion analysis in terms of skin lesion segmentation and disease classification is of great importance. However, these two tasks are challenging as skin lesion images of multi-ethnic population are collected using various scanners in multiple international medical institutes. To address them, most recent works adopt convolutional neural networks (CNNs) for skin lesion analysis. However, due to the intrinsic locality of the convolution operator, CNNs lack the ability to capture contextual information and long-range dependency. To improve the baseline performance established by CNNs, we propose a Fully Transformer Network (FTN) to learn long-range contextual information for skin lesion analysis. FTN is a hierarchical Transformer computing features using Spatial Pyramid Transformer (SPT). SPT has linear computational complexity as it introduces a spatial pyramid pooling (SPP) module into multi-head attention (MHA)to largely reduce the computation and memory usage. We conduct extensive skin lesion analysis experiments to verify the effectiveness and efficiency of FTN using ISIC 2018 dataset. Our experimental results show that FTN consistently outperforms other state-of-the-art CNNs in terms of computational efficiency and the number of tunable parameters due to our efficient SPT and hierarchical network structure. The code and models will be public available at: https://github.com/Novestars/Fully-Transformer-Network. [ABSTRACT FROM AUTHOR]

Background: Pancreatic cysts in autosomal dominant polycystic kidney disease (ADPKD) correlate with PKD2 mutations, which have a different phenotype than PKD1 mutations. However, pancreatic cysts are commonly overlooked by radiologists. Here, we automate the detection of pancreatic cysts on abdominal MRI in ADPKD., Methods: Eight nnU-Net-based segmentation models with 2D or 3D configuration and various loss functions were trained on positive-only or positive-and-negative datasets, comprising axial and coronal T2-weighted MR images from 254 scans on 146 ADPKD patients with pancreatic cysts labeled independently by two radiologists. Model performance was evaluated on test subjects unseen in training, comprising 40 internal, 40 external, and 23 test-retest reproducibility ADPKD patients., Results: Two radiologists agreed on 52% of cysts labeled on training data, and 33%/25% on internal/external test datasets. The 2D model with a loss of combined dice similarity coefficient and cross-entropy trained with the dataset with both positive and negative cases produced an optimal dice score of 0.7 ± 0.5/0.8 ± 0.4 at the voxel level on internal/external validation and was thus used as the best-performing model. In the test-retest, the optimal model showed superior reproducibility (83% agreement between scan A and B) in segmenting pancreatic cysts compared to six expert observers (77% agreement). In the internal/external validation, the optimal model showed high specificity of 94%/100% but limited sensitivity of 20%/24%., Conclusions: Labeling pancreatic cysts on T2 images of the abdomen in patients with ADPKD is challenging, deep learning can help the automated detection of pancreatic cysts, and further image quality improvement is warranted.

Total kidney volume measured on MRI is an important biomarker for assessing the progression of autosomal dominant polycystic kidney disease and response to treatment. However, we have noticed that there can be substantial differences in the kidney volume measurements obtained from the various pulse sequences commonly included in an MRI exam. Here we examine kidney volume measurement variability among five commonly acquired MRI pulse sequences in abdominal MRI exams in 105 patients with ADPKD. Right and left kidney volumes were independently measured by three expert observers using model-assisted segmentation for axial T2, coronal T2, axial single-shot fast spin echo (SSFP), coronal SSFP, and axial 3D T1 images obtained on a single MRI from ADPKD patients. Outlier measurements were analyzed for data acquisition errors. Most of the outlier values (88%) were due to breathing during scanning causing slice misregistration with gaps or duplication of imaging slices ( n = 35), slice misregistration from using multiple breath holds during acquisition ( n = 25), composing of two overlapping acquisitions ( n = 17), or kidneys not entirely within the field of view ( n = 4). After excluding outlier measurements, the coefficient of variation among the five measurements decreased from 4.6% pre to 3.2%. Compared to the average of all sequences without errors, TKV measured on axial and coronal T2 weighted imaging were 1.2% and 1.8% greater, axial SSFP was 0.4% greater, coronal SSFP was 1.7% lower and axial T1 was 1.5% lower than the mean, indicating intrinsic measurement biases related to the different MRI contrast mechanisms. In conclusion, MRI data acquisition errors are common but can be identified using outlier analysis and excluded to improve organ volume measurement consistency. Bias toward larger volume measurements on T2 sequences and smaller volumes on axial T1 sequences can also be mitigated by averaging data from all error-free sequences acquired.

Solid electrolyte interphase (SEI) formation and H 2 O activity reduction in Water-in-Salt electrolytes (WiSE) with an enlarged stability window of 3.0 V have provided the feasibility of the high-energy-density aqueous Li-ion batteries. Here, we extend the cathodic potential of WiSE by rationally controlling intermolecular interaction and interphase chemistry with the introduction of trimethyl phosphate (TMP) into WiSE. The TMP not merely limits the H 2 O activity via the strong interaction between TMP and H 2 O but also contributes to the formation of reinforced SEI involving phosphate and LiF by manipulating the Li + solvation structure. Thus, water-tolerance LiMn 2 O 4 (LMO)||Li 4 Ti 5 O 12 (LTO) full cell with a P/N ratio of 1.14 can be assembled and achieve a long cycling life of 1000 times with high coulombic efficiency of >99.9 %. This work provides a promising insight into the cost-effective practical manufacture of LMO||LTO cells without rigorous moisture-free requirements., (© 2022 Wiley-VCH GmbH.)

LiNi x Co y Mn z O 2 (x+y+z=1)||graphite lithium-ion battery (LIB) chemistry promises practical applications. However, its low-temperature (≤ -20 °C) performance is poor because the increased resistance encountered by Li + transport in and across the bulk electrolytes and the electrolyte/electrode interphases induces capacity loss and battery failures. Though tremendous efforts have been made, there is still no effective way to reduce the charge transfer resistance (R ct ) which dominates low-temperature LIBs performance. Herein, we propose a strategy of using low-polarity-solvent electrolytes which have weak interactions between the solvents and the Li + to reduce R ct , achieving facile Li + transport at sub-zero temperatures. The exemplary electrolyte enables LiNi 0.8 Mn 0.1 Co 0.1 O 2 ||graphite cells to deliver a capacity of ≈113 mAh g -1 (98 % full-cell capacity) at 25 °C and to remain 82 % of their room-temperature capacity at -20 °C without lithium plating at 1/3C. They also retain 84 % of their capacity at -30 °C and 78 % of their capacity at -40 °C and show stable cycling at 50 °C., (© 2022 Wiley-VCH GmbH.)

The capacity of transition metal oxide cathode for Li-ion batteries can be further enhanced by increasing the charging potential. However, these high voltage cathodes suffer from fast capacity decay because the large volume change of cathode breaks the active materials and cathode-electrolyte interphase (CEI), resulting in electrolyte penetration into broken active materials and continuous side reactions between cathode and electrolytes. Herein, a robust LiF-rich CEI was formed by potentiostatic reduction of fluorinated electrolyte at a low potential of 1.7 V. By taking LiCoO 2 as a model cathode, we demonstrate that the LiF-rich CEI maintains the structural integrity and suppresses electrolyte penetration at a high cut-off potential of 4.6 V. The LiCoO 2 with LiF-rich CEI exhibited a capacity of 198 mAh g -1 at 0.5C and an enhanced capacity retention of 63.5 % over 400 cycles as compared to the LiF-free LiCoO 2 with only 17.4 % of capacity retention., (© 2022 The Authors. Angewandte Chemie International Edition published by Wiley-VCH GmbH.)

Organic electrode materials are promising for green and sustainable lithium-ion batteries. However, the high solubility of organic materials in the liquid electrolyte results in the shuttle reaction and fast capacity decay. Herein, azo compounds are firstly applied in all-solid-state lithium batteries (ASSLB) to suppress the dissolution challenge. Due to the high compatibility of azobenzene (AB) based compounds to Li 3 PS 4 (LPS) solid electrolyte, the LPS solid electrolyte is used to prevent the dissolution and shuttle reaction of AB. To maintain the low interface resistance during the large volume change upon cycling, a carboxylate group is added into AB to provide 4-(phenylazo) benzoic acid lithium salt (PBALS), which could bond with LPS solid electrolyte via the ionic bonding between oxygen in PBALS and lithium ion in LPS. The ionic bonding between the active material and solid electrolyte stabilizes the contact interface and enables the stable cycle life of PBALS in ASSLB., (© 2018 Wiley-VCH Verlag GmbH & Co. KGaA, Weinheim.)

Tin and its compounds hold promise for the development of high-capacity anode materials that could replace graphitic carbon used in current lithium-ion batteries. However, the introduced porosity in current electrode designs to buffer the volume changes of active materials during cycling does not afford high volumetric performance. Here, we show a strategy leveraging a sulfur sacrificial agent for controlled utility of void space in a tin oxide/graphene composite anode. In a typical synthesis using the capillary drying of graphene hydrogels, sulfur is employed with hard tin oxide nanoparticles inside the contraction hydrogels. The resultant graphene-caged tin oxide delivers an ultrahigh volumetric capacity of 2123 mAh cm -3 together with good cycling stability. Our results suggest not only a conversion-type composite anode that allows for good electrochemical characteristics, but also a general synthetic means to engineering the packing density of graphene nanosheets for high energy storage capabilities in small volumes.